StanceAttack: Adversarial Attack for Stance Detection
Chenye Zhao, Cornelia Caragea
University of Illinois Chicago
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
Stance detection aims to ascertain whether an author's text is in favor, against, or neutral toward specific targets like public policies or social issues.While pretrained language models (PLMs) have greatly enhanced stance detection, they remain vulnerable to adversarial attacks-manipulations that maintain textual semantics but lead to incorrect predictions.Such vulnerabilities remain underexplored for stance detection.In this study, we introduce StanceAttack, an innovative adversarial attack method leveraging ChatGPT to create adversarial examples that can mislead well-trained stance detection models.We conduct experiments to evaluate our attack model by attacking state-of-theart PLMs on two benchmark datasets.Results demonstrate that StanceAttack outperforms traditional adversarial methods with higher success rates and fewer retries.Human evaluations confirm that our adversarial examples preserve the original semantic meanings and naturalness.We share our code and data in https://github.com/chenyez/StanceAttack.
逐年被引趋势
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AIAdversarial Robustness in Machine Learning
Hate Speech and Cyberbullying Detection · Topic Modeling